OCSplats: Observation Completeness Quantification and Label Noise Separation in 3DGS

TL;DR

OCSplats introduces a novel framework for quantifying observation completeness and separating label noise in 3D Gaussian Splatting, significantly improving reconstruction accuracy and noise classification across diverse real-world scenarios.

Contribution

The paper proposes OCSplats, a new method that effectively separates noise from true signals in 3DGS using epistemic uncertainty and adaptive noise classification, without scene-specific tuning.

Findings

Achieves superior reconstruction performance across various scenes.

Provides precise label noise classification in complex environments.

Demonstrates robustness to different noise proportions without parameter adjustment.

Abstract

3D Gaussian Splatting (3DGS) has become one of the most promising 3D reconstruction technologies. However, label noise in real-world scenarios-such as moving objects, non-Lambertian surfaces, and shadows-often leads to reconstruction errors. Existing 3DGS-Bsed anti-noise reconstruction methods either fail to separate noise effectively or require scene-specific fine-tuning of hyperparameters, making them difficult to apply in practice. This paper re-examines the problem of anti-noise reconstruction from the perspective of epistemic uncertainty, proposing a novel framework, OCSplats. By combining key technologies such as hybrid noise assessment and observation-based cognitive correction, the accuracy of noise classification in areas with cognitive differences has been significantly improved. Moreover, to address the issue of varying noise proportions in different scenarios, we have designed a label noise classification pipeline based on dynamic anchor points. This pipeline enables OCSplats to be applied simultaneously to scenarios with vastly different noise proportions without adjusting parameters. Extensive experiments demonstrate that OCSplats always achieve leading reconstruction performance and precise label noise classification in scenes of different complexity levels.